CN110633841B - Provincial range plot scale data assimilation yield prediction method based on set sampling - Google Patents
Provincial range plot scale data assimilation yield prediction method based on set sampling Download PDFInfo
- Publication number
- CN110633841B CN110633841B CN201910745823.XA CN201910745823A CN110633841B CN 110633841 B CN110633841 B CN 110633841B CN 201910745823 A CN201910745823 A CN 201910745823A CN 110633841 B CN110633841 B CN 110633841B
- Authority
- CN
- China
- Prior art keywords
- lai
- yield
- track
- data
- assimilation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Abstract
The invention belongs to the field of agricultural remote sensing, and relates to a provincial-scale range plot scale rapid data assimilation yield prediction method based on collective sampling, which specifically comprises the following steps: acquiring a provincial crop space distribution map based on the remote sensing data of the time sequence and the crop sample points; calibrating a WOFOST model based on site LAI and yield to obtain a posterior sample set of key parameters, inputting the posterior sample set and meteorological data of the whole growth period into the WOFOST model, and generating an LAI track set and a unit yield set in the growth period corresponding to the site; inverting the reflectivity data into LAI based on a PROSAIL model, and obtaining the LAI track range in the growth period; and carrying out reverse distance weighting on the unit yield corresponding to each obtained LAI track according to the LAI track range, wherein the yield obtained by weighted summation is the unit yield of rapid assimilation. The method can predict the crop yield per unit in a large area in a provincial range in a high-resolution plot scale of 10 meters, and has high assimilation speed and high efficiency.
Description
Technical Field
The invention belongs to the field of agricultural remote sensing, and particularly relates to a provincial-scale region plot scale rapid data assimilation yield prediction method based on collective sampling.
Background
The traditional crop yield estimation method mainly comprises a statistical investigation method, a forecasting method based on a crop model, an agricultural weather forecasting method and the like. These methods have inherent limitations that make it difficult to estimate regional crop yield with high accuracy. The estimation method based on the satellite remote sensing technology has the advantage of being unique in regional crop yield estimation by virtue of the characteristics of spatial continuity and temporal dynamics. Meanwhile, the remote sensing technology is combined with a crop growth model based on the mechanism processes of crop photosynthesis, respiration, transpiration, nutrition and the like, so that the aim of regional high-precision yield estimation can be achieved. The data assimilation method can combine the advantages of the crop growth model on point and remote sensing observation, and becomes a hotspot of research on agricultural quantitative remote sensing at home and abroad in recent years.
However, in the existing assimilation estimation method, the cost function of remote sensing observation and a crop model is constructed by a four-dimensional variation method through field crop pixel by field crop pixel, and the input parameters of the crop model are obtained through multiple iterations. The method for integrating Kalman filtering assimilation updates and optimizes state variables (LAI, soil moisture, biomass and the like) by introducing effective remote sensing observation data of crop growth period. When remote sensing data with the spatial resolution of 10-30m is introduced and the size of the assimilation unit grid is 10-30m, massive assimilation data can be formed. At present, the traditional grid-by-grid assimilation strategy is difficult to meet the actual demand of real-time yield prediction.
Disclosure of Invention
In order to solve the following problems in the prior art of assimilation estimation: when the data assimilation grid unit is 10-30m, massive assimilation data are formed. In the traditional data assimilation process, the state variables of a crop model need to be updated all the time or the crop model needs to be reinitialized, so that the assimilation execution efficiency is low, the assimilation execution speed is low, and the yield application requirement of a plot scale in a large regional space range is difficult to meet.
The invention provides a provincial-scale block scale rapid data assimilation yield prediction method based on collective sampling, which comprises the following specific steps of:
s1, acquiring provincial crop space distribution maps by adopting a random forest method based on Landsat8 and sentinel No. 2 remote sensing data and crop sample points of time sequences;
s2, calibrating the WOFOST model by using an MCMC (multi-sample multi-carrier) method based on site LAI (local area interference) and yield data to obtain a posterior sample set of key parameters of the WOFOST model;
s3, the posterior sample set obtained in the step S2 is used as a key parameter set, and the posterior sample set and meteorological data in the whole growth period are input into a WOFOST model together to generate an LAI track set and a unit yield set in the growth period corresponding to the station;
s4, inverting remote sensing reflectivity data of sentinel 2 to LAI based on a PROSAIL model to obtain an LAI mean value and a standard deviation of each LAI grid and obtain an LAI track range in a growth period;
and S5, according to the LAI track range of S4, carrying out reverse distance weighting on the crop unit yield corresponding to each LAI track obtained in the S3, wherein the yield obtained by weighted summation is the unit yield obtained by rapid assimilation.
Wherein, the meteorological data of the whole growth period of S3: live meteorological data is used from emergence to the point of onset of forecast, and meteorological forecast data is used after the point of onset of forecast.
Wherein, the site LAI and yield data of S2 are actually measured sample point data, such as agricultural gas observation site data.
Wherein, the step S2 specifically includes: and (3) observing the Leaf Area Index (LAI) of the crop at the site unit yield and the crop at the site in the key growth period and corresponding uncertain estimated values (empirical values) of the Leaf Area Index (LAI) and the site unit yield, and estimating posterior probability distribution of WOFOST crop growth model parameters in the site by adopting MCMC (multi-channel controller), so as to obtain a posterior sample set of key parameters.
The key parameters are key parameters of a wobest crop growth model, such as TSUM1, SPAN, TDWI, and the like.
Wherein, the step S3 specifically includes: and (4) inputting the parameter posterior sample set obtained in the step (S2) into a WOFOST model to generate an LAI track set and a single-unit-yield set, wherein one LAI track set corresponds to one single unit yield.
Wherein, the step S4 specifically includes: firstly, atmospheric correction is carried out on sentinel 2 data, then the sentinel data is inverted into LAI data according to the resolution of a 10m grid multiplied by 10m grid based on a PROSAIL model, an LAI track in a growth period is obtained, the mean value of each grid LAI is the median value of a group of corresponding LAIs when the cost function of the grid converges, the standard deviation is the standard deviation of the group of LAIs, the upper boundary and the lower boundary (the upper boundary is the mean value plus the labeling difference, and the lower boundary is the mean value minus the standard deviation) of the LAI track are generated according to the mean value and the standard deviation of the LAI obtained through inversion, and the LAI track range in the growth period is obtained.
The inversion of step S4 may employ any conventional LAI inversion algorithm.
Wherein, the step S5 is as follows: based on the LAI track range obtained by inversion in step S4, screening the track set generated in step S3 corresponding to the site closest to the center point of the LAI grid; performing inverse distance weighted summation on the unit yield corresponding to the LAI track, wherein the weight is the negative first power of the distance between the LAI track in the step S3 and the LAI track corresponding to the LAI mean value of each grid obtained in the step S4; the yield obtained by the weighted summation is the unit yield average value of the rapid assimilation, and the standard deviation of the unit yield set corresponding to the screened LAI track set is the standard deviation of the rapid assimilation.
Wherein the crop is one of staple grain crops such as wheat, rice, corn and the like, and winter wheat is preferred.
The invention also provides application of the provincial scale rapid data assimilation yield prediction method based on the collective sampling in guiding crop production.
Compared with the prior art, the invention has the beneficial effects that:
the area assimilated by the invention is a large area estimate of high spatial resolution. Limited by the efficiency of an assimilation algorithm, the number of field measured samples and other factors, the spatial resolution of general assimilation estimation is 250 meters to 1 kilometer, and once data are assimilated and introduced into data of a block scale (10 meters spatial resolution, namely 10m multiplied by 10m grids), massive assimilation units, namely hundreds of millions of assimilation units, can be generated. For one province, the conventional method needs to be operated for 1 month. The method can complete assimilation within 10 hours.
The invention has high assimilation speed. Different from the traditional assimilation method for updating the state variables of the crop model or reinitializing the crop model, the method realizes the mapping of the LAI track set and the single-yield set by utilizing the idea of set sampling, thereby realizing the prediction of the single yield of the crop in a large area on the 10-meter spatial resolution.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 shows that in step S3 of embodiment 1 of the present invention, the obtained posterior sample set is used as a key parameter set and input into the wobest model together with the meteorological data of the whole growth period, so as to generate a simulated LAI trajectory curve in the growth period corresponding to the station.
Fig. 3 is an LAI time series trajectory range diagram obtained by inverting remote sensing reflectivity data of sentinel No. 2 into LAI based on the PROSAIL model in step S4 in embodiment 1 of the present invention.
Fig. 4 is an effect diagram obtained by superimposing the simulated LAI trajectory curve of fig. 2 and the LAI time series trajectory range diagram of the remote sensing inversion LAI of fig. 3 in embodiment 1 of the present invention.
Fig. 5 is a region diagram in which the range of the remote sensing inversion LAI interval and the simulated LAI trajectory curve are superimposed and then the intersection of the curve clusters is circled to be an empty set in embodiment 1 of the present invention, which is shown as excluded, and the simulated LAI set in the ellipse in the diagram is very inconsistent with the inversion result of sentinel No. 2, and is considered to be unlikely to occur, that is, a low weight may be ignored or given.
FIG. 6 is a graph showing aggregate yield prediction in example 1 of the present invention.
Detailed Description
The following describes in further detail specific embodiments of the present invention with reference to examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Example 1
The provincial scale rapid data assimilation yield prediction method based on the collective sampling estimates the yield of the water-balanced winter wheat, and the specific flow is shown in figure 1.
The balance water was selected as the study area. Remote sensing reflectivity data of Sentinel 2(Sentinel-2A/AB) in the research area from 1 month to 6 months in 2018 are selected.
S1, acquiring provincial winter wheat spatial distribution maps by adopting a random forest method based on Landsat8 and sentinel 2 remote sensing data of time sequences and winter wheat sample points.
S2, calibrating the WOFOST model by using an MCMC method based on site LAI and yield data to obtain a posterior sample set of the WOFOST model key parameters.
The site LAI and the yield data are actually measured sample point data, and agricultural gas observation station data is adopted in the embodiment.
Step S2 specifically includes: and (3) observing the Leaf Area Index (LAI) of the crop at the site unit yield and the crop at the site in the key growth period and corresponding uncertain estimated values (empirical values) of the Leaf Area Index (LAI) and the site unit yield, and estimating posterior probability distribution of WOFOST crop growth model parameters in the site by adopting MCMC (multi-channel controller), so as to obtain a posterior sample set of key parameters. The key parameters are key parameters of a wobest crop growth model, such as TSUM1, SPAN, TDWI, and the like.
And S3, taking the posterior sample set obtained in the step S2 as a key parameter set, inputting the posterior sample set and meteorological data of the whole growth period into a WOFOST model, and generating an LAI track set and a unit yield set in the growth period corresponding to the station, wherein a curve of the generated LAI track is specifically shown in the figure 2.
Meteorological data for the entire growth period: live meteorological data is used from emergence to the point of onset of forecast, and meteorological forecast data is used after the point of onset of forecast.
The step S3 specifically includes: and (4) inputting the parameter posterior sample set obtained in the step (S2) into a WOFOST model to generate an LAI track set and a single-unit-yield set, wherein one LAI track set corresponds to one single unit yield.
S4, inverting remote sensing reflectivity data of sentinel 2 to obtain LAI based on a PROSAIL model, obtaining an LAI mean value and a standard deviation of each LAI grid, and obtaining an LAI track range in a growth period.
Step S4 specifically includes: firstly, atmospheric correction is carried out on sentinel 2 data, then the sentinel data is inverted into LAI data according to the resolution of a 10m grid multiplied by 10m grid based on a PROSAIL model, an LAI track in a growth period is obtained, the mean value of each grid LAI is the median value of a group of corresponding LAIs when the cost function of the grid converges, the standard deviation is the standard deviation of the group of LAIs, the upper boundary and the lower boundary (the upper boundary is the mean value plus the labeling difference, and the lower boundary is the mean value minus the standard deviation) of the LAI track are generated according to the mean value and the standard deviation of the LAI obtained through inversion, and the LAI track range in the growth period is obtained, and specifically shown in figure 3. The inversion described in step S4 may employ any conventional LAI inversion algorithm.
And S5, according to the LAI track range of S4, carrying out reverse distance weighting on the unit yield of the winter wheat corresponding to each LAI track obtained in the S3, wherein the yield obtained by weighted summation is the unit yield obtained by rapid assimilation.
The step S5 is specifically as follows: based on the LAI track range obtained by the inversion in the step S4, screening the track set generated in the step S3 corresponding to the site closest to the center point of the LAI grid, i.e., superimposing the fig. 2 and the fig. 3, wherein a superimposed effect diagram is shown in fig. 4, excluding the area in which the simulated LAI set in the fig. 4 is very inconsistent with the sentinel No. 2 inversion result, obtaining fig. 5, ignoring the circled area in fig. 5, performing inverse distance weighted summation on the individual yields corresponding to the LAI track, and taking the weight as the negative primary power of the distance between the LAI track in the step S3 and the LAI track corresponding to the LAI mean value of each grid obtained in the step S4; the yield obtained by the weighted summation is the average value of the rapidly assimilated single products, the obtained aggregate yield prediction graph is shown in FIG. 6, and the standard deviation of the single product aggregate corresponding to the screened LAI track aggregate is the standard deviation of the rapid assimilation.
The assimilation area of the invention is provincial scale large area estimated production with high spatial resolution of 10 meters. The invention has high assimilation speed and completes assimilation within 10 hours.
Although the invention has been described in detail hereinabove with respect to a general description and specific embodiments thereof, it will be apparent to those skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (8)
1. A provincial-scale block scale rapid data assimilation yield prediction method based on collective sampling is characterized by comprising the following specific steps:
s1, acquiring provincial crop space distribution maps by adopting a random forest method based on the Landsat8 and sentinel No. 2 remote sensing data of the time sequence and crop sample points;
s2, calibrating the WOFOST model by using an MCMC method based on site LAI and yield data to obtain a posterior sample set of the WOFOST model key parameters;
s3, the posterior sample set obtained in the step S2 is used as a key parameter set, and the key parameter set and meteorological data of the whole growth period are input into a WOFOST model together to generate an LAI track set and a unit yield set in the growth period corresponding to the station;
s4, inverting the remote sensing reflectivity data of sentinel No. 2 into LAI based on a PROSAIL model to obtain the LAI mean value and standard deviation of each LAI grid and obtain the LAI track range in the growth period;
and S5, according to the LAI track range of S4, carrying out reverse distance weighting on the crop unit yield corresponding to each LAI track obtained in the S3, wherein the yield obtained by weighted summation is the unit yield obtained by rapid assimilation.
2. The method for forecasting provincial-scale parcel-scale rapid data assimilation yield based on collective sampling as claimed in claim 1, wherein the meteorological data of the whole growth period of S3: live meteorological data is used from emergence to the point of onset of forecast, and meteorological forecast data is used after the point of onset of forecast.
3. The method for forecasting provincial-wide block scale fast data assimilation yield based on collective sampling as claimed in claim 2, wherein the step S2 is specifically as follows: and (3) observing the key growth period LAI of the crop measured by the site per unit yield and the site and the corresponding uncertain estimated values of the LAI and the LAI, and estimating the posterior probability distribution of the WOFOST crop growth model parameters in the site by adopting MCMC to obtain a posterior sample set of the key parameters.
4. The method for forecasting provincial-wide block scale fast data assimilation yield based on collective sampling as claimed in claim 2, wherein the step S3 is specifically as follows: and (4) inputting the parameter posterior sample set obtained in the step (S2) into a WOFOST model to generate an LAI track set and a single-unit-yield set, wherein one LAI track set corresponds to one single unit yield.
5. The method for forecasting provincial-wide block scale fast data assimilation yield based on collective sampling as claimed in claim 2, wherein the step S4 is specifically as follows: firstly, atmospheric correction is carried out on sentinel 2 data, then the sentinel data is inverted into LAI data according to the resolution of a 10m multiplied by 10m grid based on a PROSAIL model, an LAI track in a growth period is obtained, the LAI mean value of each LAI grid is the median value of a group of corresponding LAIs when the cost function of the grid is converged, the standard deviation is the standard deviation of the group of LAIs, and the upper and lower boundaries of the LAI track are generated according to the average value and the standard deviation of the LAIs obtained through inversion, so that the LAI track range in the growth period is obtained.
6. The method for forecasting provincial-wide block scale fast data assimilation yield based on collective sampling as claimed in claim 1, wherein the step S5 is as follows: based on the LAI track range obtained by inversion in step S4, screening the track set generated in step S3 corresponding to the site closest to the center point of the LAI grid; performing inverse distance weighted summation on the unit yield corresponding to the LAI track, wherein the weight is the negative first power of the distance between the LAI track in the step S3 and the LAI track corresponding to the LAI mean value of each LAI grid obtained in the step S4; the yield obtained by the weighted summation is the unit yield average value of the rapid assimilation, and the standard deviation of the unit yield set corresponding to the screened LAI track set is the standard deviation of the rapid assimilation.
7. The method for rapid data assimilation yield prediction based on the provincial wide plot scale of the collective sampling as claimed in any one of claims 1 to 6, wherein the crop is one of wheat, rice and corn.
8. A method for directing crop production, comprising the set-sampling based provincial-wide plot scale fast data assimilation yield prediction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745823.XA CN110633841B (en) | 2019-08-13 | 2019-08-13 | Provincial range plot scale data assimilation yield prediction method based on set sampling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745823.XA CN110633841B (en) | 2019-08-13 | 2019-08-13 | Provincial range plot scale data assimilation yield prediction method based on set sampling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110633841A CN110633841A (en) | 2019-12-31 |
| CN110633841B true CN110633841B (en) | 2022-04-01 |
Family
ID=68970390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910745823.XA Active CN110633841B (en) | 2019-08-13 | 2019-08-13 | Provincial range plot scale data assimilation yield prediction method based on set sampling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110633841B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111898922B (en) * | 2020-08-10 | 2021-07-06 | 深圳市大德众和科技有限公司 | Multi-scale crop yield assessment method and system |
| CN112052988B (en) * | 2020-08-18 | 2024-03-22 | 中国农业大学 | Crop yield estimation method coupling multi-objective optimization and collection assimilation and application |
| CN113705937B (en) * | 2021-10-27 | 2022-01-14 | 武汉大学 | Farmland yield estimation method combining machine vision and crop model |
| CN115753625B (en) * | 2022-11-02 | 2024-04-19 | 中国农业大学 | Yield estimation method and device for regional crops, electronic equipment and storage medium |
| CN116071644B (en) * | 2022-12-20 | 2023-08-08 | 中化现代农业有限公司 | Method, device, equipment and storage medium for inversion of sun leaf area index data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2007125088A (en) * | 2007-07-02 | 2009-01-10 | Учреждение Ханты-Мансийского автономного округа-Югры "Югорский научно-исследовательский институт информационных технологий" (RU) | METHOD FOR PREDICTING YIELD OF GRAIN CROPS BASED ON SPACE MONITORING DATA AND BIOPRODUCTIVITY SIMULATION |
| CN103955860A (en) * | 2014-04-17 | 2014-07-30 | 中国农业大学 | Regional crop yield estimation method based on ensemble Kalman filter assimilation |
| CN104134095A (en) * | 2014-04-17 | 2014-11-05 | 中国农业大学 | Crop yield estimation method based on scale transformation and data assimilation |
| CN108509836A (en) * | 2018-01-29 | 2018-09-07 | 中国农业大学 | Crop yield estimation method based on double-polarized synthetic aperture radar and crop model data assimilation |
| CN109754125A (en) * | 2019-01-18 | 2019-05-14 | 中国农业大学 | Crop yield forecast method based on crop modeling, history and meteorological forecast data |
| CN109800921A (en) * | 2019-01-30 | 2019-05-24 | 北京师范大学 | A kind of Regional Fall Wheat yield estimation method based on remote sensing phenology assimilation and particle swarm optimization algorithm |
-
2019
- 2019-08-13 CN CN201910745823.XA patent/CN110633841B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2007125088A (en) * | 2007-07-02 | 2009-01-10 | Учреждение Ханты-Мансийского автономного округа-Югры "Югорский научно-исследовательский институт информационных технологий" (RU) | METHOD FOR PREDICTING YIELD OF GRAIN CROPS BASED ON SPACE MONITORING DATA AND BIOPRODUCTIVITY SIMULATION |
| CN103955860A (en) * | 2014-04-17 | 2014-07-30 | 中国农业大学 | Regional crop yield estimation method based on ensemble Kalman filter assimilation |
| CN104134095A (en) * | 2014-04-17 | 2014-11-05 | 中国农业大学 | Crop yield estimation method based on scale transformation and data assimilation |
| CN108509836A (en) * | 2018-01-29 | 2018-09-07 | 中国农业大学 | Crop yield estimation method based on double-polarized synthetic aperture radar and crop model data assimilation |
| CN109754125A (en) * | 2019-01-18 | 2019-05-14 | 中国农业大学 | Crop yield forecast method based on crop modeling, history and meteorological forecast data |
| CN109800921A (en) * | 2019-01-30 | 2019-05-24 | 北京师范大学 | A kind of Regional Fall Wheat yield estimation method based on remote sensing phenology assimilation and particle swarm optimization algorithm |
Non-Patent Citations (3)
| Title |
|---|
| Assimilating SAR and optical remote sensing data into WOFOST model for improving winter wheat yield estimation;Wen Zhuo 等;《2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics)》;20181001;全文 * |
| 基于MCMC方法的WOFOST模型参数标定与不确定性分析;黄健熙 等;《农业工程学报》;20180831;第34卷(第16期);全文 * |
| 遥感与作物生长模型数据同化应用综述;黄健熙 等;《农业工程学报》;20181130;第34卷(第21期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110633841A (en) | 2019-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110633841B (en) | Provincial range plot scale data assimilation yield prediction method based on set sampling | |
| CN110751094A (en) | Crop yield estimation technology based on GEE comprehensive remote sensing image and deep learning method | |
| Oettli et al. | Are regional climate models relevant for crop yield prediction in West Africa? | |
| WO2020132092A1 (en) | Apparatus and method for crop yield prediction | |
| CN106951979A (en) | The crop maturity phase Forecasting Methodology that remote sensing, crop modeling are merged with weather forecast | |
| Ovando et al. | Evaluating accuracy of DSSAT model for soybean yield estimation using satellite weather data | |
| CN111898922B (en) | Multi-scale crop yield assessment method and system | |
| CN111027175A (en) | Method for evaluating social and economic influences of flood based on coupling model integrated simulation | |
| CN112052988B (en) | Crop yield estimation method coupling multi-objective optimization and collection assimilation and application | |
| CN113592132B (en) | Rainfall objective forecasting method based on numerical weather forecast and artificial intelligence | |
| Terando et al. | Observed and modeled twentieth-century spatial and temporal patterns of selected agro-climate indices in North America | |
| CN107038501B (en) | R language-based wheat growth period characteristic parameter estimation method | |
| CN111915096B (en) | Crop yield early-stage forecasting technology based on crop model, remote sensing data and climate forecasting information | |
| CN116522145B (en) | Drought prediction method considering space-time constraint and vegetation condition | |
| Li et al. | Predicting maize yield in Northeast China by a hybrid approach combining biophysical modelling and machine learning | |
| CN115936238B (en) | Method, system, equipment and medium for predicting medium-long-term output of global wind power | |
| CN109615150B (en) | Method and system for determining rice meteorological output | |
| Sepulcre-Cantó et al. | Estimating crop-specific evapotranspiration using remote-sensing imagery at various spatial resolutions for improving crop growth modelling | |
| CN116485757A (en) | Winter wheat total nitrogen content prediction method | |
| Kiyoshi et al. | FieldTouch: an innovative agriculture decision support service based on multi-scale sensor platform | |
| CN114239274A (en) | Method for calculating root layer soil water by multi-source remote sensing data driven index filtering model | |
| Li et al. | Crop model data assimilation with particle filter for yield prediction using leaf area index of different temporal scales | |
| Huang et al. | Markov chain monte carlo and four-dimensional variational approach based winter wheat yield estimation | |
| CN116595333B (en) | Soil-climate intelligent rice target yield and nitrogen fertilizer consumption determination method | |
| Pepelyaev et al. | Modeling the Impact of Climate Change on the Crop Yield |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |